Selecting or Solving? What Best-of-N Verification Delivers in Video Reasoning
cs.CV
Submitted: 2026-10-31
Updated: 2026-10-31
Code: https://github.com/facebookresearch/best-n-selection-video-reasoning
Terminology
Sources
- Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone
- Perception First: A Frontier Native-Video Model with Self-Consistency for Implicit Video Question Answering
- Benchmarking and Mitigating MCQA Selection Bias of Large Vision-Language Models
- Large Language Monkeys: Scaling Inference Compute with Repeated Sampling
- One Ranking, Any Budget: Matryoshka Evidence-to-Context Frame Selection for Long-Video Understanding
- Video-Holmes: Can MLLM Think Like Holmes for Complex Video Reasoning?
- Training Verifiers to Solve Math Word Problems
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- With Tools or Because of Tools? Tracing Capability Gains in Multimodal Agents
- VTAgent: Agentic Keyframe Anchoring for Evidence-Aware Video TextVQA
- Don't Show Pixels, Show Cues: Unlocking Visual Tool Reasoning in Language Models via Perception Programs
- Accuracy Without Grounding: Diagnosing Visual Dependency Dissociation in Video LLM Benchmarks
- Let's Verify Step by Step
- TempCompass: Do Video LLMs Really Understand Videos?
- Addressing Blind Guessing: Calibration of Selection Bias in Multiple-Choice Question Answering by Video Language Models
- EgoSchema: A Diagnostic Benchmark for Very Long-form Video Language Understanding
- MoReVQA: Exploring Modular Reasoning Models for Video Question Answering
- A Cost-Aware, Paired Protocol for Auditing Dynamic Tool Synthesis in Agentic Video Question Answering
- s1: Simple test-time scaling
- Reliability without Validity: A Systematic, Large-Scale Evaluation of LLM-as-a-Judge Models Across Agreement, Consistency, and Bias
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs